Download - Log Normal

Transcript
Page 1: Log Normal

Log normal distribution (from http://www.math.wm.edu/˜leemis/chart/UDR/UDR.html)

The shorthand X ∼ log normal(α, β) is used to indicate that the random variable X has the log

normal distribution with parameters α and β. A log normal random variable X with parameters α

and β has probability density function

f (x) =1

xβ√

2πe−

12 (ln(x/α)/β)2

x > 0

for α and β > 0. The log normal distribution can be used to model the lifetime of an object, the

weight of a person, or a service time. The central limit theorem indicates that the log normal

distribution is useful for modeling random variables that can be thought of as a product of several

independent random variables. The probability density function with three different parameter

settings is illustrated below.

0 2 4 6 8 10

0.0

0.2

0.4

0.6

0.8

1.0

α=1, β=1

α=1, β=2

α=5, β=0.5

x

f (x)

The cumulative distribution function on the support of X is

F(x) = P(X ≤ x) =1

2+

1

2erf

(√2(ln(x)−α)

)

x > 0,

where

erf(x) =2√

π

∫ x

0e−t2

dt.

The survivor function on the support of X is

S(x) = P(X ≥ x) =1

2−

1

2erf

(√2(ln(x)−α)

)

x > 0.

The hazard function on the support of X is

h(x) =f (x)

S(x)=−

√2e−(ln(x)−α)2/2β2 1

√π

x−1β−1

(

−1+ erf

(√2(ln(x)−α)

))−1

x > 0.

1

Page 2: Log Normal

The cumulative hazard function on the support of X is

H(x) =− lnS(x) = ln(2)+ iπ− ln

(

−1+ erf

(√2(ln(x)−α)

))

x > 0.

The inverse distribution function, moment generating function, and characteristic function of X are

mathematically intractable.

The median of X is α.

The population mean, variance, skewness, and kurtosis of X are

E[X ] = αeβ2/2 V [X ] = α2eβ2

(eβ2

−1)

E

[

(

X −µ

σ

)3]

= (eβ2

+2)(eβ2

−1)1/2 E

[

(

X −µ

σ

)4]

= e4β2

+2e3β2

+3e2β2

−3

APPL verification: The APPL statements

assume(alpha > 0);

assume(beta > 0);

X := [[x-> (1/(x*beta*sqrt(2*Pi)))*exp((-1/2)*(ln(x/alpha)/beta)ˆ2)],

[0,infinity],["Continuous","PDF"]];

CDF(X);

SF(X);

HF(X);

CHF(X);

Mean(X);

Variance(X);

Skewness(X);

Kurtosis(X);

verify the cumulative distribution function, survivor function, hazard function, cumulative hazard

function, population mean, variance, skewness, and kurtosis.

2


Top Related